GLM-5.3 Flash
GLM-5.3 Flash
zai/glm-5.3-flash
Overview
Capabilities
Tool callingVisionStructured outputReasoningStreaming
Pricing (lowest)
$0.015/M / $0.05/M
Context window
1M
Modality
Multimodal
Hosts
4 hosts
Vendor details
| Z.AI | Particle | Wafer | Baseten | |
|---|---|---|---|---|
| Input cost | $0.015/M | $0.015/M | $0.15/M | $0.15/M |
| Output cost | $0.05/M | $0.05/M | $0.50/M | $0.50/M |
| Cache read cost | $0.003/M | $0.003/M | $0.03/M | $0.03/M |
| Currency | USD | USD | USD | USD |
| Availability | available | available | available | available |
| Context window | 1M | 1M | 1M | 1M |
| Max output | 131K | 131K | 131K | 262K |
| Zero data retention | No | Yes | No | Yes |
| Launched | Aug 2026 | Aug 2026 | Aug 2026 | Aug 2026 |
| Capabilities | Tool callingStreaming | Tool callingStreaming | Tool callingStreaming | Tool callingStreaming |
| Reasoning effort levels | lowhighmax | lowhighmax | lowhighmax | lowhighmax |
| Modalities | Input: TextInput: ImageInput: DocumentInput: VideoOutput: TextOutput: Tool use | Input: TextInput: ImageInput: DocumentInput: VideoOutput: TextOutput: Tool use | Input: TextInput: ImageInput: DocumentInput: VideoOutput: TextOutput: Tool use | Input: TextInput: ImageInput: DocumentInput: VideoOutput: TextOutput: Tool use |